English

On-chip Face Recognition System Design with Memristive Hierarchical Temporal Memory

Emerging Technologies 2017-09-26 v1

Abstract

Hierarchical Temporal Memory is a new machine learning algorithm intended to mimic the working principle of neocortex, part of the human brain, which is responsible for learning, classification, and making predictions. Although many works illustrate its effectiveness as a software algorithm, hardware design for HTM remains an open research problem. Hence, this work proposes an architecture for HTM Spatial Pooler and Temporal Memory with learning mechanism, which creates a single image for each class based on important and unimportant features of all images in the training set. In turn, the reduction in the number of templates within database reduces the memory requirements and increases the processing speed. Moreover, face recognition analysis indicates that for a large number of training images, the proposed design provides higher accuracy results (83.5\%) compared to only Spatial Pooler design presented in the previous works.

Keywords

Cite

@article{arxiv.1709.08184,
  title  = {On-chip Face Recognition System Design with Memristive Hierarchical Temporal Memory},
  author = {Timur Ibrayev and Ulan Myrzakhan and Olga Krestinskaya and Aidana Irmanova and Alex Pappachen James},
  journal= {arXiv preprint arXiv:1709.08184},
  year   = {2017}
}

Comments

Journal of Intelligent and Fuzzy Systems, 2018

R2 v1 2026-06-22T21:53:01.708Z